pacman.operations.placer_algorithms package¶
Module contents¶

class
pacman.operations.placer_algorithms.
RadialPlacer
¶ Bases:
object
A placement algorithm that can place a machine graph onto a machine choosing chips radiating in a circle from the boot chip

__call__
(machine_graph, machine, plan_n_timesteps)[source]¶ Parameters:  machine_graph (MachineGraph) – The machine_graph to place
 machine (Machine) – The machine with respect to which to partition the application graph
 plan_n_timesteps (int) – number of timesteps to plan for
Returns: A set of placements
Return type: Raises: PacmanPlaceException – If something goes wrong with the placement


class
pacman.operations.placer_algorithms.
OneToOnePlacer
¶ Bases:
pacman.operations.placer_algorithms.RadialPlacer
Placer that puts vertices which are directly connected to only its destination on the same chip

__call__
(machine_graph, machine, plan_n_timesteps)[source]¶ Parameters:  machine_graph (MachineGraph) – The machine_graph to place
 machine (Machine) – The machine with respect to which to partition the application graph
 plan_n_timesteps (int) – number of timesteps to plan for
Returns: A set of placements
Return type: Raises: PacmanPlaceException – If something goes wrong with the placement


class
pacman.operations.placer_algorithms.
SpreaderPlacer
¶ Bases:
pacman.operations.placer_algorithms.OneToOnePlacer
Places vertices on as many chips as available with a effort to reduce the number of packets being received by the router in total.
Parameters:  machine_graph (MachineGraph) – the machine graph
 machine (Machine) – the SpiNNaker machine
 n_keys_map (AbstractMachinePartitionNKeysMap) – the n keys from partition map
 plan_n_timesteps (int) – number of timesteps to plan for
Returns: placements.
Return type: 
ITERATIONS
= 4¶

STEPS
= 4¶

__call__
(machine_graph, machine, n_keys_map, plan_n_timesteps)[source]¶ Parameters:  machine_graph (MachineGraph) – the machine graph
 machine (Machine) – the SpiNNaker machine
 n_keys_map (AbstractMachinePartitionNKeysMap) – the n keys from partition map
 plan_n_timesteps (int) – number of timesteps to plan for
Returns: placements.
Return type:

class
pacman.operations.placer_algorithms.
ConnectiveBasedPlacer
¶ Bases:
pacman.operations.placer_algorithms.RadialPlacer
A radial algorithm that can place a machine graph onto a machine using a circle out behaviour from a Ethernet at a given point and which will place things that are most connected closest to each other

__call__
(machine_graph, machine, plan_n_timesteps)[source]¶ Parameters:  machine_graph (MachineGraph) – The machine_graph to place
 machine (Machine) – The machine with respect to which to partition the application graph
 plan_n_timesteps (int) – number of timesteps to plan for
Returns: A set of placements
Return type: Raises: PacmanPlaceException – If something goes wrong with the placement
